spacetimeformer
spacetimeformer copied to clipboard
QData
Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."
I am using model : spacetimeformer and dataset: asos. When I run `python train.py spacetimeformer asos --run_name test --gpus 0` I get this error. `TypeError: accuracy() missing 1 required positional...
Hello! I wonder if you used any random seed for reproducibility and if so, where I could find the seeds used. Thank you!
Hi, I'm trying to install spacetimeformer on Colab following this code: ``` !git clone https://github.com/QData/spacetimeformer.git !cd spacetimeformer !conda create -n spacetimeformer python==3.8 !conda activate spacetimeformer !pip install -r requirements.txt !pip...
I know it's stated that the training process runs on an outdated version of lightning and torchmetrics, but I couldn't find a way to run it using any of the...
Hi, I'd like to use, for example, LSTM for univariate time series (TSa) forecasting given multivariate time series (including the target ones, e.g., TSa, TSb, and TSc) as inputs. Is...
I get an error after running the installation instructions and trying the `-h` command: `python train.py spacetimeformer -h` # Full tracebacks ``` Traceback (most recent call last): File "train.py", line...
Default Time Emb Dim is 6, however, the paper states that the value used was 12. The example training commands don't specify this hyper parameter. To recreate the results in...
Hey there! I loved the paper and the approach you had with this. I wonder if there is a guidance or idea of how to make inference of new data.
Hello, I'm working on a project using data from a longitudinal study that has many subjects tied to exam dates and associated features at each of those exam dates. Looking...
